Quantum Machine Learning Research & Innovation
Published work, ongoing research, and experimental ideas from IITGN QuantumLab.
Research Vision
Our research explores the intersection of Quantum Machine Learning, Cyber Security, and NISQ-era quantum systems. We aim to design quantum-enhanced algorithms that are theoretically grounded and practically deployable on near-term quantum hardware.
Key focus areas include quantum kernel methods, variational quantum circuits, quantum generative models, and hybrid quantum–classical learning pipelines.
This page serves as a living archive of our published research, experimental systems, and future research directions.
Published Research
Leveraging Quantum Kernel Methods for Enhanced Intrusion Detection
A systematic evaluation of Quantum Support Vector Machines (QSVM) for intrusion detection using quantum kernels and feature maps.
- ZZFeatureMap-based quantum kernel construction
- Evaluated on CICIDS2017, NSL-KDD, CIDDS-001, UGR’16
- Up to 98% reduction in false positives
- Best performance in low-dimensional feature spaces
Key Insight
Quantum kernels create sharper class separation, improving precision and reliability of IDS under NISQ constraints.
Quantum GAN for Synthetic Anomalous Data Generation
A Quantum Generative Adversarial Network (QGAN) designed to generate synthetic anomalous network traffic.
- Variational quantum generator circuits
- Synthetic anomaly generation for IDS training
- Improves generalization on rare attack classes
- Addresses data imbalance and privacy concerns
Key Insight
QGAN-generated data improves robustness of IDS models without relying on sensitive real-world traffic.
Ongoing & Exploratory Research
Noise-Resilient VQC
Designing circuit ansätze resilient to barren plateaus and hardware noise.
Quantum Anomaly Detection
Fidelity-based unsupervised quantum models for anomaly detection.
Hybrid Quantum LSTM
Temporal modeling using quantum-enhanced recurrent architectures.
Submit Your Research
Have you worked on something exciting? Submit your findings below. Approved submissions will be showcased on our platform.
Collaborate With Us
Interested in joining the lab, or exploring ideas together?
Contact Research Team